IQLAgent<T>

Models & Types · AiDotNet.ReinforcementLearning.Agents.IQL

Implicit Q-Learning (IQL) agent for offline reinforcement learning.

Inheritance: ReinforcementLearningAgentBase<T> → DeepReinforcementLearningAgentBase<T> → IQLAgent<T>

Implements: IGeneratedParameterRegistrar<T>, IGradientComputable<T, Vector<T>, Vector<T>>

For Beginners

IQL is an offline RL algorithm that learns from fixed datasets. It uses a clever statistical technique (expectile regression) to avoid overestimating values of unseen actions.

Key features:

  • Expectile Regression: Asymmetric loss that focuses on upper quantiles
  • Three Networks: V(s), Q(s,a), and π(a|s)
  • Simpler than CQL: No conservative penalties or Lagrangian multipliers
  • Advantage-Weighted Regression: Extracts policy from Q and V functions

Think of expectiles like percentiles - focusing on “typically good” outcomes rather than “best possible” outcomes helps avoid overoptimism.

Advantages:

  • Simpler hyperparameter tuning than CQL
  • Often more stable
  • Good for offline datasets with diverse quality

How It Works

IQL uses expectile regression to learn a value function that focuses on high-return trajectories, enabling effective offline policy learning without explicit conservative penalties like CQL.

Example

// Create an Implicit Q-Learning agent for offline RL
var options = new IQLOptions<double> { StateSize = 4, ActionSize = 2, Expectile = 0.7 };
var agent = new IQLAgent<double>(options);
            
// Select an action using advantage-weighted regression
var state = new Vector<double>(new double[] { 0.5, -0.3, 1.0, 0.2 });
var action = agent.SelectAction(state);

Constructors

Constructor Summary
IQLAgent() Initializes a new instance with default settings.
IQLAgent(IQLOptions<T> options)

Properties

Property Summary
int FeatureCount { get; }

Methods

Method Summary
Dictionary<string, T> GetMetrics()
ModelMetadata<T> GetModelMetadata()
ModelOptions GetOptions()
T Train()
Task TrainAsync()
Task<Vector<T>> PredictAsync(Vector<T> input)
Vector<T> ComputeGradients(Vector<T> input, Vector<T> target, ILossFunction<T> lossFunction)
Vector<T> Predict(Vector<T> input)
Vector<T> SelectAction(Vector<T> state, bool training)
byte[] Serialize() Auto-generated common model serialization surface.
void ApplyGradients(Vector<T> gradients, T learningRate)
void Deserialize(byte[] data) Auto-generated common model deserialization surface.
void LoadModel(string filepath)
void LoadOfflineData(List<ValueTuple<Vector<T>, Vector<T>, T, Vector<T>, bool>> dataset) Load offline dataset into the replay buffer.
void ResetEpisode()
void SaveModel(string filepath)
void StoreExperience(Vector<T> state, Vector<T> action, T reward, Vector<T> nextState, bool done)